gokul
commited on
Commit
•
3523b4c
1
Parent(s):
4536841
Model upload
Browse files- config.json +1 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"_name_or_path": "bert-base-uncased", "architectures": ["BertForTokenClassification"], "attention_probs_dropout_prob": 0.1, "classifier_dropout": null, "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "id2label": {"0": "O", "1": "B-CARDINAL", "2": "B-DATE", "3": "B-EVENT", "4": "B-FAC", "5": "B-GPE", "6": "B-LANGUAGE", "7": "B-LAW", "8": "B-LOC", "9": "B-MONEY", "10": "B-NORP", "11": "B-ORDINAL", "12": "B-ORG", "13": "B-PERCENT", "14": "B-PERSON", "15": "B-PRODUCT", "16": "B-QUANTITY", "17": "B-TIME", "18": "B-WORK_OF_ART", "19": "I-CARDINAL", "20": "I-DATE", "21": "I-EVENT", "22": "I-FAC", "23": "I-GPE", "24": "I-LANGUAGE", "25": "I-LAW", "26": "I-LOC", "27": "I-MONEY", "28": "I-NORP", "29": "I-ORDINAL", "30": "I-ORG", "31": "I-PERCENT", "32": "I-PERSON", "33": "I-PRODUCT", "34": "I-QUANTITY", "35": "I-TIME", "36": "I-WORK_OF_ART"}, "initializer_range": 0.02, "intermediate_size": 3072, "label2id": {"O": "0", "B-CARDINAL": "1", "B-DATE": "2", "B-EVENT": "3", "B-FAC": "4", "B-GPE": "5", "B-LANGUAGE": "6", "B-LAW": "7", "B-LOC": "8", "B-MONEY": "9", "B-NORP": "10", "B-ORDINAL": "11", "B-ORG": "12", "B-PERCENT": "13", "B-PERSON": "14", "B-PRODUCT": "15", "B-QUANTITY": "16", "B-TIME": "17", "B-WORK_OF_ART": "18", "I-CARDINAL": "19", "I-DATE": "20", "I-EVENT": "21", "I-FAC": "22", "I-GPE": "23", "I-LANGUAGE": "24", "I-LAW": "25", "I-LOC": "26", "I-MONEY": "27", "I-NORP": "28", "I-ORDINAL": "29", "I-ORG": "30", "I-PERCENT": "31", "I-PERSON": "32", "I-PRODUCT": "33", "I-QUANTITY": "34", "I-TIME": "35", "I-WORK_OF_ART": "36"}, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "bert", "num_attention_heads": 12, "num_hidden_layers": 12, "pad_token_id": 0, "position_embedding_type": "absolute", "torch_dtype": "float32", "transformers_version": "4.41.0", "type_vocab_size": 2, "use_cache": true, "vocab_size": 30522}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1d872b90c4f72269ecfcc6ea7a54565937f884feebf3a84a4b1ec12ce7f0f4e
|
3 |
+
size 435703748
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "BertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|